sync: update ggml

ggml_extend.hpp

@@ -846,7 +846,7 @@ public:
             return NULL;
         }
         // it's performing a compute, check if backend isn't cpu
-        if (!ggml_backend_is_cpu(backend) && tensor->backend == GGML_BACKEND_CPU) {
+        if (!ggml_backend_is_cpu(backend) && tensor->backend == GGML_BACKEND_TYPE_CPU) {
             // pass input tensors to gpu memory
             auto backend_tensor = ggml_dup_tensor(compute_ctx, tensor);
 

stable-diffusion.h

@@ -76,6 +76,9 @@ enum sd_type_t {
     SD_TYPE_IQ3_XXS = 18,
     SD_TYPE_IQ1_S   = 19,
     SD_TYPE_IQ4_NL  = 20,
+    SD_TYPE_IQ3_S   = 21,
+    SD_TYPE_IQ2_S   = 22,
+    SD_TYPE_IQ4_XS  = 23,
     SD_TYPE_I8,
     SD_TYPE_I16,
     SD_TYPE_I32,